Domande per il Colloquio da Senior System Administrator: Guida Completa

# Elenca le VM
virsh list --all

# Avvia la VM
virsh start vm-name

# Crea la VM da XML
virsh define vm-config.xml

# Clona la VM
virt-clone --original vm1 --name vm2 --auto-clone

# Allocazione delle risorse della VM
virsh setmem vm-name 4G
virsh setvcpus vm-name 4

# Installa il software del cluster
sudo apt install pacemaker corosync pcs

# Configura l'autenticazione del cluster
sudo passwd hacluster
sudo pcs cluster auth node1 node2 -u hacluster

# Crea il cluster
sudo pcs cluster setup --name mycluster node1 node2

# Avvia il cluster
sudo pcs cluster start --all
sudo pcs cluster enable --all

# Disabilita STONITH per i test (abilitalo in produzione)
sudo pcs property set stonith-enabled=false

# Crea la risorsa IP virtuale
sudo pcs resource create virtual_ip ocf:heartbeat:IPaddr2 \
    ip=192.168.1.100 cidr_netmask=24 \
    op monitor interval=30s

# Crea la risorsa del servizio web
sudo pcs resource create webserver ocf:heartbeat:apache \
    configfile=/etc/apache2/apache2.conf \
    statusurl="http://localhost/server-status" \
    op monitor interval=1min

# Raggruppa le risorse
sudo pcs resource group add webgroup virtual_ip webserver

# Imposta i vincoli delle risorse
sudo pcs constraint colocation add webserver with virtual_ip INFINITY
sudo pcs constraint order virtual_ip then webserver

# Controlla lo stato del cluster
sudo pcs status
sudo crm_mon -1

# Installa keepalived
sudo apt install keepalived

# Configura sul Master
sudo vi /etc/keepalived/keepalived.conf

vrrp_instance VI_1 {
    state MASTER
    interface eth0
    virtual_router_id 51
    priority 100
    advert_int 1
    
    authentication {
        auth_type PASS
        auth_pass secret123
    }
    
    virtual_ipaddress {
        192.168.1.100/24
    }
    
    track_script {
        chk_nginx
    }
}

vrrp_script chk_nginx {
    script "/usr/bin/killall -0 nginx"
    interval 2
    weight 2
}

# Configurazione del Master
[mysqld]
server-id = 1
log_bin = /var/log/mysql/mysql-bin.log
binlog_do_db = production

# Crea l'utente di replica
CREATE USER 'repl'@'%' IDENTIFIED BY 'password';
GRANT REPLICATION SLAVE ON *.* TO 'repl'@'%';
FLUSH PRIVILEGES;

# Ottieni lo stato del master
SHOW MASTER STATUS;

# Configurazione dello Slave
[mysqld]
server-id = 2
relay-log = /var/log/mysql/mysql-relay-bin
log_bin = /var/log/mysql/mysql-bin.log
read_only = 1

# Configura lo slave
CHANGE MASTER TO
    MASTER_HOST='master-ip',
    MASTER_USER='repl',
    MASTER_PASSWORD='password',
    MASTER_LOG_FILE='mysql-bin.000001',
    MASTER_LOG_POS=107;

START SLAVE;
SHOW SLAVE STATUS\G

#!/bin/bash
# Script di controllo dell'integrità del servizio

check_service() {
    if systemctl is-active --quiet $1; then
        return 0
    else
        return 1
    fi
}

if ! check_service nginx; then
    echo "Nginx down, tentativo di riavvio"
    systemctl restart nginx
    sleep 5
    if ! check_service nginx; then
        echo "Nginx non è riuscito a riavviarsi, attivazione del failover"
        # Attiva il failover
        pcs resource move webgroup node2
    fi
fi

# Simula il guasto del nodo
sudo pcs cluster stop node1

# Verifica il failover
sudo pcs status
ping 192.168.1.100

# Ripristina il nodo
sudo pcs cluster start node1

#!/bin/bash
# Controllo automatizzato dell'integrità del server

HOSTNAME=$(hostname)
DATE=$(date '+%Y-%m-%d %H:%M:%S')
REPORT="/var/log/health-check.log"

echo "=== Controllo di Integrità: $DATE ===" >> $REPORT

# Carico della CPU
LOAD=$(uptime | awk -F'load average:' '{print $2}')
echo "Carico Medio: $LOAD" >> $REPORT

# Utilizzo della Memoria
MEM=$(free -h | grep Mem | awk '{print "Usata: "$3" / "$2}')
echo "Memoria: $MEM" >> $REPORT

# Utilizzo del Disco
echo "Utilizzo del Disco:" >> $REPORT
df -h | grep -vE '^Filesystem|tmpfs|cdrom' >> $REPORT

# Servizi Falliti
FAILED=$(systemctl --failed --no-pager)
if [ -n "$FAILED" ]; then
    echo "Servizi Falliti:" >> $REPORT
    echo "$FAILED" >> $REPORT
fi

# Invia un avviso se critico
DISK_USAGE=$(df -h / | tail -1 | awk '{print $5}' | sed 's/%//')
if [ $DISK_USAGE -gt 90 ]; then
    echo "CRITICO: Utilizzo del disco superiore al 90%" | mail -s "Avviso: $HOSTNAME" [email protected]
fi

---
- name: Configura i server web
  hosts: webservers
  become: yes
  tasks:
    - name: Installa i pacchetti
      apt:
        name:
          - nginx
          - python3
          - git
        state: present
        update_cache: yes
    
    - name: Copia la configurazione di nginx
      template:
        src: nginx.conf.j2
        dest: /etc/nginx/nginx.conf
      notify: riavvia nginx
    
    - name: Assicurati che nginx sia in esecuzione
      service:
        name: nginx
        state: started
        enabled: yes
  
  handlers:
    - name: riavvia nginx
      service:
        name: nginx
        state: restarted

# inventory/production
[webservers]
web[01:20].company.com

[databases]
db[01:05].company.com

[loadbalancers]
lb[01:02].company.com

[webservers: vars]
ansible_user=deploy
ansible_become=yes

# playbooks/site.yml
---
- name: Configura tutti i server
  hosts: all
  roles:
    - common
    - security
    - monitoring

- name: Configura i server web
  hosts: webservers
  roles:
    - nginx
    - php
    - application
  
- name: Configura i database
  hosts: databases
  roles:
    - mysql
    - backup

# roles/common/tasks/main.yml
---
- name: Aggiorna tutti i pacchetti
  apt:
    upgrade: dist
    update_cache: yes
    cache_valid_time: 3600

- name: Installa i pacchetti comuni
  apt:
    name:
      - vim
      - htop
      - curl
      - git
    state: present

- name: Configura NTP
  template:
    src: ntp.conf.j2
    dest: /etc/ntp.conf
  notify: riavvia ntp

- name: Assicurati che i servizi siano in esecuzione
  service:
    name: "{{ item }}"
    state: started
    enabled: yes
  loop:
    - ntp
    - rsyslog

#!/usr/bin/env python3
# dynamic_inventory.py - Inventario dinamico AWS EC2

import json
import boto3

def get_inventory():
    ec2 = boto3.client('ec2')
    response = ec2.describe_instances()
    
    inventory = {
        '_meta': {'hostvars': {}},
        'all': {'hosts': []}
    }
    
    for reservation in response['Reservations']:
        for instance in reservation['Instances']:
            if instance['State']['Name'] != 'running':
                continue
            
            hostname = instance['PrivateIpAddress']
            inventory['all']['hosts'].append(hostname)
            
            # Raggruppa per tag
            for tag in instance.get('Tags', []):
                if tag['Key'] == 'Role':
                    role = tag['Value']
                    if role not in inventory:
                        inventory[role] = {'hosts': []}
                    inventory[role]['hosts'].append(hostname)
    
    return inventory

if __name__ == '__main__':
    print(json.dumps(get_inventory(), indent=2))

# Workflow Git
git checkout -b feature/update-nginx-config
# Apporta modifiche
git add .
git commit -m "Aggiorna la configurazione SSL di nginx"
git push origin feature/update-nginx-config
# Crea una pull request per la revisione

# Controlla la sintassi del playbook
ansible-playbook --syntax-check site.yml

# Esecuzione a secco
ansible-playbook site.yml --check

# Esegui prima in staging
ansible-playbook -i inventory/staging site.yml

# Distribuisci in produzione
ansible-playbook -i inventory/production site.yml

# Ansible Vault
ansible-vault create secrets.yml
ansible-vault encrypt vars/passwords.yml
ansible-playbook site.yml --ask-vault-pass

# Oppure usa un file di password
ansible-playbook site.yml --vault-password-file ~/.vault_pass

# Errato - non idempotente
- name: Aggiungi una riga al file
  shell: echo "config=value" >> /etc/app.conf

# Corretto - idempotente
- name: Assicurati che la riga di configurazione esista
  lineinfile:
    path: /etc/app.conf
    line: "config=value"
    state: present

# Esegui su 10 host alla volta
ansible-playbook -i inventory site.yml --forks 10

# Limita a host specifici
ansible-playbook site.yml --limit webservers

# Esegui tag specifici
ansible-playbook site.yml --tags "configuration,deploy"

#!/bin/bash
# Backup automatizzato con conservazione

BACKUP_SOURCE="/var/www /etc /home"
BACKUP_DEST="/mnt/backup"
REMOTE_SERVER="backup.company.com"
RETENTION_DAYS=30

# Crea il backup
DATE=$(date +%Y%m%d)
tar -czf $BACKUP_DEST/backup-$DATE.tar.gz $BACKUP_SOURCE

# Sincronizza con il server remoto
rsync -avz --delete $BACKUP_DEST/ $REMOTE_SERVER:/backups/

# Pulisci i vecchi backup
find $BACKUP_DEST -name "backup-*.tar.gz" -mtime +$RETENTION_DAYS -delete

# Verifica il backup
tar -tzf $BACKUP_DEST/backup-$DATE.tar.gz > /dev/null
if [ $? -eq 0 ]; then
    echo "Backup verificato con successo"
else
    echo "Verifica del backup fallita!" | mail -s "Avviso di Backup" [email protected]
fi

# Configurazione MySQL Master-Slave
# Sul Master:
CHANGE MASTER TO
  MASTER_HOST='master-server',
  MASTER_USER='repl_user',
  MASTER_PASSWORD='password',
  MASTER_LOG_FILE='mysql-bin.000001',
  MASTER_LOG_POS=107;

START SLAVE;
SHOW SLAVE STATUS\G

# Aggiornamenti di sicurezza automatizzati (Ubuntu)
sudo apt install unattended-upgrades
sudo dpkg-reconfigure -plow unattended-upgrades

# /etc/ssh/sshd_config
Port 2222  # Cambia la porta predefinita
PermitRootLogin no
PasswordAuthentication no
PubkeyAuthentication yes
AllowUsers admin devops
MaxAuthTries 3
ClientAliveInterval 300
ClientAliveCountMax 2

# Regole iptables
iptables -P INPUT DROP
iptables -P FORWARD DROP
iptables -P OUTPUT ACCEPT

# Consenti connessioni stabilite
iptables -A INPUT -m state --state ESTABLISHED,RELATED -j ACCEPT

# Consenti SSH (porta personalizzata)
iptables -A INPUT -p tcp --dport 2222 -j ACCEPT

# Consenti HTTP/HTTPS
iptables -A INPUT -p tcp --dport 80 -j ACCEPT
iptables -A INPUT -p tcp --dport 443 -j ACCEPT

# Salva le regole
iptables-save > /etc/iptables/rules.v4

# Installa AIDE
sudo apt install aide
sudo aideinit

# Controlla le modifiche
sudo aide --check

# Abilita auditd
sudo systemctl enable auditd
sudo systemctl start auditd

# Monitora l'accesso ai file
sudo auditctl -w /etc/passwd -p wa -k passwd_changes
sudo auditctl -w /etc/shadow -p wa -k shadow_changes

# CPU
mpstat 1 10

# Memoria
vmstat 1 10

# I/O del Disco
iostat -x 1 10

# Rete
iftop
nethogs

# Ottimizzazione Nginx
worker_processes auto;
worker_connections 4096;
keepalive_timeout 65;
gzip on;
gzip_types text/plain text/css application/json;

# Ottimizzazione MySQL
innodb_buffer_pool_size = 4G
max_connections = 200
query_cache_size = 64M

# /etc/sysctl.conf
net.core.somaxconn = 4096
net.ipv4.tcp_max_syn_backlog = 4096
net.ipv4.tcp_fin_timeout = 30
vm.swappiness = 10
fs.file-max = 100000

# Prometheus + Grafana
# Node Exporter per le metriche di sistema
# Avvisi personalizzati per le soglie

# prometheus.yml
global:
  scrape_interval: 15s
  evaluation_interval: 15s

scrape_configs:
  - job_name: 'node'
    static_configs:
      - targets:
        - 'server1:9100'
        - 'server2:9100'
        - 'server3:9100'
  
  - job_name: 'mysql'
    static_configs:
      - targets: ['db1:9104']
  
  - job_name: 'nginx'
    static_configs:
      - targets: ['web1:9113']

alerting:
  alertmanagers:
    - static_configs:
      - targets: ['localhost:9093']

rule_files:
  - 'alerts/*.yml'

# alerts/system.yml
groups:
  - name: system_alerts
    interval: 30s
    rules:
      - alert: HighCPUUsage
        expr: 100 - (avg by(instance) (irate(node_cpu_seconds_total{mode="idle"}[5m])) * 100) > 80
        for: 5m
        labels:
          severity: warning
        annotations:
          summary: "Elevato utilizzo della CPU su {{ $labels.instance }}"
          description: "L'utilizzo della CPU è del {{ $value }}%"
      
      - alert: HighMemoryUsage
        expr: (node_memory_MemTotal_bytes - node_memory_MemAvailable_bytes) / node_memory_MemTotal_bytes * 100 > 90
        for: 5m
        labels:
          severity: critical
        annotations:
          summary: "Elevato utilizzo della memoria su {{ $labels.instance }}"
          description: "L'utilizzo della memoria è del {{ $value }}%"
      
      - alert: DiskSpaceLow
        expr: (node_filesystem_avail_bytes{mountpoint="/"} / node_filesystem_size_bytes{mountpoint="/"}) * 100 < 10
        for: 5m
        labels:
          severity: critical
        annotations:
          summary: "Spazio su disco insufficiente su {{ $labels.instance }}"
          description: "Rimane solo il {{ $value }}% di spazio su disco"
      
      - alert: ServiceDown
        expr: up == 0
        for: 2m
        labels:
          severity: critical
        annotations:
          summary: "Servizio {{ $labels.job }} non funzionante"
          description: "{{ $labels.instance }} non è funzionante da più di 2 minuti"

# alertmanager.yml
global:
  resolve_timeout: 5m
  slack_api_url: 'https://hooks.slack.com/services/YOUR/WEBHOOK/URL'

route:
  group_by: ['alertname', 'cluster']
  group_wait: 10s
  group_interval: 10s
  repeat_interval: 12h
  receiver: 'default'
  routes:
    - match:
        severity: critical
      receiver: 'pagerduty'
      continue: true
    - match:
        severity: warning
      receiver: 'slack'

receivers:
  - name: 'default'
    email_configs:
      - to: '[email protected]'
        from: '[email protected]'
        smarthost: 'smtp.company.com:587'
  
  - name: 'slack'
    slack_configs:
      - channel: '#alerts'
        title: '{{ .GroupLabels.alertname }}'
        text: '{{ range .Alerts }}{{ .Annotations.description }}{{ end }}'
  
  - name: 'pagerduty'
    pagerduty_configs:
      - service_key: 'YOUR_PAGERDUTY_KEY'

inhibit_rules:
  - source_match:
      severity: 'critical'
    target_match:
      severity: 'warning'
    equal: ['alertname', 'instance']

{
  "dashboard": {
    "title": "Panoramica del Sistema",
    "panels": [
      {
        "title": "Utilizzo della CPU",
        "targets": [
          {
            "expr": "100 - (avg by(instance) (irate(node_cpu_seconds_total{mode=\"idle\"}[5m])) * 100)"
          }
        ]
      },
      {
        "title": "Utilizzo della Memoria",
        "targets": [
          {
            "expr": "(node_memory_MemTotal_bytes - node_memory_MemAvailable_bytes) / node_memory_MemTotal_bytes * 100"
          }
        ]
      }
    ]
  }
}

# Esempio SLO
- alert: SLOViolation
  expr: |
    (
      sum(rate(http_requests_total{status=~"2.."}[30d]))
      /
      sum(rate(http_requests_total[30d]))
    ) < 0.999
  labels:
    severity: critical
  annotations:
    summary: "Violazione SLO: tasso di successo inferiore al 99,9%"

# Crea una GPO
New-GPO -Name "Security Policy" -Comment "Impostazioni di sicurezza aziendali"

# Collega a una OU
New-GPLink -Name "Security Policy" -Target "OU=Servers,DC=company,DC=com"

# Configura la policy delle password
Set-ADDefaultDomainPasswordPolicy -Identity company.com `
    -MinPasswordLength 12 `
    -PasswordHistoryCount 24 `
    -MaxPasswordAge 90.00:00:00

# Distribuisci software tramite GPO
# Configurazione Computer > Criteri > Impostazioni Software > Installazione Software

# Configura WSUS
Set-ItemProperty -Path "HKLM:\SOFTWARE\Policies\Microsoft\Windows\WindowsUpdate" `
    -Name "WUServer" -Value "http://wsus.company.com:8530"

# Forza il controllo degli aggiornamenti
wuauclt /detectnow /updatenow

# Abilita il remoting
Enable-PSRemoting -Force

# Esegui su più server
Invoke-Command -ComputerName server1,server2,server3 -ScriptBlock {
    Get-Service | Where-Object {$_.Status -eq "Stopped"}
}

# Esecuzione parallela
$servers = Get-Content servers.txt
$servers | ForEach-Object -Parallel {
    Test-Connection -ComputerName $_ -Count 1
} -ThrottleLimit 10